Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/silenceinsect/aidocxworkflow/agents-mdgit clone --depth 1 https://github.com/SilenceInsect/AIDocxWorkFlowWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01861 | $0.01861 |
| Opus 5 | $0.00931 | $0.00931 |
| Sonnet 5 | $0.00372 | $0.00372 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade A, and why
AIDocxWorkFlow AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIDocxWorkFlow 项目铁律
本文件是项目根级入口——Cursor 启动会话自动加载，每次回答前必读。 范围：只写项目级原则；阶段细则放
.mdc/SKILL.md/MODULES.md。
最高准则（决策顺序 = 优先级）
-
一致性优先 — 改之前先看是否让设计 / 约束 / 实现 / 测试 / 文档失配
-
设计优先 — 先判断结构对不对，再判断能不能快做完
-
全局考虑优先 — 不按"分锅"优化，按项目整体工程化质量；指标：可执行 / 可审查 / 可理解 / 可维护 / 可追溯
-
人本可审查 — 输出给具体名词看、不堆术语、有执行清单、不凭空、不无根据
-
辩证求真 — 遇到分歧不停留于"堆选项"，分四步走：
a. 论题：显式写出当前方案的"核心主张是什么"（≤1 句话）
b. 反题：追问"对立面成立的条件是什么"——不是反驳，而是找它的合理性边界
c. 合题：在反题边界内修正论题，形成新命题；明确保留什么、废除什么
d. 验证：用具体场景检验合题是否自洽；若仍存分歧，写入
open_questions.md入下一轮，不强行收敛反模式：跳步（直接给 3 个选项却不写论题）、反题空转（反驳但找不到成立条件）、无验证合题
示例：
论题：identity card 应该装方法论知识 反题：知识无法溯源时怎么办？ 合题：框架层放方法论（本身即来源），示例层显式标注
示例：，来源可疑的具体断言迁入 module_templates/ 验证：LINK 特色节是否还有未经标注的具体断言？
结构性反模式（违反任一 = 方案失败）
- ❌ 只补局部闭环，不审全局一致性
- ❌ 代码改了，
.mdc/SKILL.md/ 文档 / 测试不对齐 - ❌ 先动手再补设计——先修实现，后补论证
- ❌ 不告诉人影响范围——改 X 影响 Y/Z 却不显式说明
Git 分类铁律（新增任何文件 / 目录前必判）
判定优先级：过程录制 > 公共知识库——所有 *.jsonl（目标反模式案例 / 反馈日志 / 阶段录制 / 录制类产物）一律不入 git，即使放在 knowledge/public/ 下也不行；公共知识库仅收录 .md / .json / .db 等可复用非录制类资产。
四类边界：
| 资产类别 | 入 git | 落点 |
|---|---|---|
功能 / 测试 / 规则 / 公共知识（.py / .mdc / .md / .json / .db） |
✅ | 默认 |
过程录制（*.jsonl / *.log / 反馈日志 / 阶段上下文包 / 反模式录制） |
❌ | .gitignore 已覆盖（*.jsonl / feedback_logs/ / workflow_assets/**/stage_context.*） |
项目级私有（knowledge/project_local/ / resource/ / workflow_assets/ / governance/ / CHANGELOG.md / .goal-log-db/） |
❌ | .gitignore 已覆盖 |
本地构建 / 缓存产物（__pycache__/ / .pytest_cache/ / dist/ 等） |
❌ | .gitignore 已覆盖 |
重要：
knowledge/public/module_templates/属公共知识库，新增 / 修改不得由通用 Agent 直接入库——先产候选，人工审核。模块专家 Agent 已落地（v34 B1）：8 业务模块（CONFIG / UI / BIZ / UTIL / LINK / SPECIAL / LOG / HINT）各自的模块专家 skill 位于
.cursor/skills/<module>-expert/SKILL.md，对自己模块（module_templates/<MY_MODULE>/+<MY_MODULE>.md）可直接写正式库（仍需 PR 留痕 + commit 标注[<MODULE>-专家直写]）；跨模块 / 公共文件（_common_structure.md/_decision_tree.md/s2_output_template.md）任何 Agent 都不得直写。索引：
.cursor/skills/_module-experts/README.md详见.cursor/rules/DESIGN_AND_EXECUTION_STANDARDS.mdc§0.1.3（主体权限对照表 + 边界自检流程）。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 88 lines · 1,861 tokens per session scan A 641ebbc52877
AIDocxWorkFlow AGENTS.md is an instructions file published in the GitHub repository SilenceInsect/AIDocxWorkFlow (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,861 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.